agentleFS
mshadmanrahmanmshadmanrahman/claude-for-designers/.claude/skills/pick-up/SKILL.md

pick-up

Skill32 starsChanged 49 days agoMITView on GitHub

Reads the newest entry of a project's log.md and tells the student where they left off: what they did and decided, what is open, and the next step. Takes an optional project name. With several projects and no name, shows a menu of each project's last entry. Read only. Use when the student says pick up, where did I leave off, read my last log, continue from yesterday, or opens a fresh chat to resume work.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read only. This skill writes nothing.

    line 8
  2. Very specific:

    Claude Code is open inside one project folder: Use that folder's log.md.

    line 17
  3. Distinctive:

    Only one log exists: Use it.

    line 18
  4. Distinctive:

    Several logs exist: Read only the first entry of each and show a menu, most recent first:

    line 19
  5. Very specific:

    If no log exists anywhere, say so in one line and point them to /wrap-up at the end of today's session.

    line 33
  6. Distinctive:

    Read the first entry under the header.

    line 37
  7. Distinctive:

    If the entry is older than two weeks, add one line: "This is from <date>, so check it still holds."

    line 53

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

The student typed /pick-up, maybe followed by a project name. This is a fresh chat and it knows nothing about yesterday. Your job is to read their last log entry and tell them where they left off, so they start working in under a minute.

Read only. This skill writes nothing.

Step 1. Find the right log

Logs live at projects/<client>/log.md and career-vault/log.md. Ignore projects/_new-client/, which is a template.

Pick the log in this order, and stop at the first one that applies:

  1. They named a project (/pick-up acme). Use that project's log. Match loosely: "acme" finds projects/acme-fintech/, "career" or "vault" finds career-vault/log.md.
  2. Claude Code is open inside one project folder. Use that folder's log.md.
  3. Only one log exists. Use it.
  4. Several logs exist. Read only the first entry of each and show a menu, most recent first:
You have three projects with a log:

  1. acme-fintech   yesterday     Next: dashboard empty states
  2. edubridge      3 days ago    Next: write scope-email.md
  3. career-vault   last week     Next: finish 02-portfolio-story.md

Which one?

Then wait for their answer.

If no log exists anywhere, say so in one line and point them to /wrap-up at the end of today's session. Then offer the normal orientation from CLAUDE.md.

Step 2. Read the newest entry only

Read the first entry under the header. Do not read older entries unless they ask. Do not read the whole project folder yet; the entry names the files that matter.

Then open the file the Next line names, if it names one, so you know its current state before you speak. If that file already looks finished, say so: they may have done more after the last wrap-up.

Step 3. Tell them, in this shape

Last time (2 Oct, Class 3) you finished the interrogated brief and
decided bKash is its own flow. Still open: who handles refunds.

Next step: write scope-email.md. Start there, or deal with the
refund question first?

Three parts, under 80 words: what they did and decided, what is still open, and the next step as a question. Use their decisions as settled. Do not reopen them unless they ask.

If the entry is older than two weeks, add one line: "This is from <date>, so check it still holds."

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.